检索结果-内蒙古大学图书馆

AlbNews: A Corpus of Headlines for Topic Modeling in Albanian

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Çano, Erion Lamaj, Dario Digital Philology Data Mining and Machine Learning University of Vienna Austria Cognitive Science Department of Applied Informatics Comenius University Bratislava Slovakia

The scarcity of available text corpora for low-resource languages like Albanian is a serious hurdle for research in natural language processing tasks. This paper introduces AlbNews, a collection of 600 topically labeled news headlines and 2600 unlabeled ones in Albanian. The data can be freely used for conducting topic modeling research. We report the initial classification scores of some traditional machine learning classifiers trained with the AlbNews samples. These results show that basic models outrun the ensemble learning ones and can serve as a baseline for future experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： learning algorithms

Thai Conversational Chatbot Classification Using BiLSTM and data Augmentation 1st

学校读者我要写书评

暂无评论

Thai Conversational Chatbot Classification Using BiLSTM and ...

1st International Conference on data science and Artificial Intelligence, DSAI 2023

作者： Lhasiw, Nunthawat Tanantong, Tanatorn Sanglerdsinlapachai, Nuttapong Thammasat Research Unit in Data Innovation and Artificial Intelligence Department of Computer Science Faculty of Science and Technology Thammasat University Pathum Thani Thailand Strategic Analytics Networks with Machine Learning and AI Research Team National Electronics and Computer Technology Center Pathum Thani Thailand

ISBN: (纸本)9789819979684

Chatbot platforms, e.g., Facebook and Line, have revolutionized human interaction in the digital age. In order to develop an automatic chatbot classification, there are several challenges especially for Thai chat messages. Conversational messages are usually short and ambiguous. Therefore, it is difficult to find a dataset for constructing an effective classification model. To address the limited size of the dataset, data augmentation techniques can be possibly applied. data augmentation involves generating synthetic messages by applying various transformations to existing data samples while preserving their original meaning. In this study, the size and diversity of the dataset is increased by two methods, i.e., text augmentation using word2vec from Thai2Fit and English-Thai machine translation models proposed by VISTEC. Based on the augmented messages, a Deep learning technique, BiLSTM, is used to construct a chatbot classification model. The experimental obtained results demonstrate that data augmentation can help to increase the classification performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Classification (of information)

Advancing Alzheimer's Nodule Detection Through a Comprehensive Multi-Scene Deep learning Framework 10

学校读者我要写书评

暂无评论

Advancing Alzheimer's Nodule Detection Through a Comprehensi...

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Premkumar, C. Rajeshwari, R. Remya, R. Cholaathiraj, M.S. Reethika, A. Bharathidasan, S. Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Sathyamangalam India Cmr Institute of Technology Department of Computer Science and Engineering Bengaluru India Vel Tech Rangarajan Dr Sagunthala R&d institute of science and Technology Department of Electronics and Communication Engineering Chennai India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Sathyamangalam India Sri Ramakrishna Engineering College Department of Electronics and Communication Engineering Coimbatore India Erode Sengunthar Engineering College Department of Electronics and Communication Engineering Erode India

ISBN: (纸本)9798350384369

Determining the precise location of Alzheimer's nodules is essential for estimating the risk of brain cancer. Conventional CAD modules, including MRI, PET, and CT, struggle with feature extraction and segmentation due to time limits and complexity. This study proposes an efficient brain nodule detection technique based on the Multi-Scene Deep learning Framework (MSDLF) that makes use of the vesselness filter. A four-channel CNN model is developed using information from two image sequences to enhance radiologists' ability to recognise four-stage nodules. This adaptable model may be used in two different classes. The outcomes demonstrate how well the MSDLF performs while processing substantial volumes of image data for brain nodule recognition, improving with accuracy 98.86% and 98.45% of sensitivity by using decreasing false positives. © 2024 IEEE.

关键词： Magnetic resonance imaging

Catoni-style confidence sequences for heavy-tailed mean estimation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Hongjian Ramdas, Aaditya Machine Learning Department Carnegie Mellon University United States Department of Statistics and Data Science Carnegie Mellon University United States

A confidence sequence (CS) is a sequence of confidence intervals that is valid at arbitrary data-dependent stopping times. These are useful in applications like A/B testing, multi-armed bandits, off-policy evaluation, election auditing, etc. We present three approaches to constructing a confidence sequence for the population mean, under the minimal assumption that only an upper bound σ2 on the variance is known. While previous works rely on light-tail assumptions like boundedness or subGaussianity (under which all moments of a distribution exist), the confidence sequences in our work are able to handle data from a wide range of heavy-tailed distributions. The best among our three methods — the Catoni-style confidence sequence — performs remarkably well in practice, essentially matching the state-of-the-art methods for σ2-subGaussian data, and provably attains the plog log t/t lower bound due to the law of the iterated logarithm. Our findings have important implications for sequential experimentation with unbounded observations, since the σ2-bounded-variance assumption is more realistic and easier to verify than σ2-subGaussianity (which implies the former). We also extend our methods to data with infinite variance, but having pth central moment (1 MSC Codes 62L12, 60G42 Copyright © 2022, The Authors. All rights reserved.

关键词：

Risk-limiting Financial Audits via Weighted Sampling without Replacement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shekhar, Shubhanshu Xu, Ziyu Lipton, Zachary C. Liang, Pierre J. Ramdas, Aaditya Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States Tepper School of Business Carnegie Mellon University United States

We introduce the notion of a risk-limiting financial auditing (RLFA): given N transactions, the goal is to estimate the total misstated monetary fraction (m∗) to a given accuracy ϵ, with confidence 1-δ. We do this by constructing new confidence sequences (CSs) for the weighted average of N unknown values, based on samples drawn without replacement according to a (randomized) weighted sampling scheme. Using the idea of importance weighting to construct test martingales, we first develop a framework to construct CSs for arbitrary sampling strategies. Next, we develop methods to improve the quality of CSs by incorporating side information about the unknown values associated with each item. We show that when the side information is sufficiently predictive, it can directly drive the sampling. Addressing the case where the accuracy is unknown a priori, we introduce a method that incorporates side information via control variates. Crucially, our construction is adaptive: if the side information is highly predictive of the unknown misstated amounts, then the benefits of incorporating it are significant;but if the side information is uncorrelated, our methods learn to ignore it. Our methods recover state-of-the-art bounds for the special case when the weights are equal, which has already found applications in election auditing. The harder weighted case solves our more challenging problem of AI-assisted financial auditing. © 2023, CC BY.

关键词： Risk perception

Attention based 1-D CNN system for detection of Freezing of gait (FOG) in Parkinsons Patients

学校读者我要写书评

暂无评论

Attention based 1-D CNN system for detection of Freezing of ...

International Conference on Computing and Networking Technology (ICCNT)

作者： D Pradeep Kumar B J Sowmya Ashvin Vincent Aravindh Pandiyan Department of Computer Science and Engineering Ramaiah Institute of Technology Bangalore India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bangalore India Machine Learning Engineer Bangalore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

One common clinical symptom seen in Parkinson’s disease (PD) patients is freezing of gait (FOG). It manifests as an irregular gait, marked by abrupt, involuntary stopping of movement during gait episodes. FOG entails a major negative effect on PD patients’ quality of life. In this work, we analyze the movement data that is collected using the lower-back 3D accelerometer worn by the patients during FOG episodes. By employing machine learning methods to classify this data, we aim to accurately detect FOG trends. In particular, we focus on Deep learning-based techniques, specifically an attention-based 1D Convolutional Neural Network (1D-CNN), due to their capacity to extract intricate features from unprocessed sensor input. Our results indicate that the proposed model achieves AUC scores of 0.9032 with respect to the TDCSFOG dataset and 0.8682 for the DeFOG dataset, for a combined average AUC of 0.8857. Mean Average Precision (mAP) scores for TDCSFOG and DeFOG reach 0.8388 and 0.779, respectively, for an average of 0.8089, showing the ability of the model to predict FOG occurrences over time. These findings suggest techniques based on Deep learning enhance FOG detection, allowing clinicians to more effectively tailor treatments and care strategies for Parkinson’s patients, thus enhancing their ability to move and overall well-being.

关键词： Deep learning Accelerometers Three-dimensional displays Accuracy Predictive models Feature extraction Transformers Convolutional neural networks Forecasting Diseases

Exploring the Tangible Impact of Artificial Intelligence and machine learning: Bridging the Gap between Hype and Reality 1

学校读者我要写书评

暂无评论

Exploring the Tangible Impact of Artificial Intelligence and...

1st International Conference on Advanced Computing and Emerging Technologies, ACET 2024

作者： Dattangire, Rahul Vaidya, Ruchika Biradar, Divya Joon, Ashish Publicis Sapient Data Engineering HoustonTX77002 United States Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India University of Texas at Arlington Computer Science ArlingtonTX76019 United States Andhus Technologies Inc Software Developer PensacolaFL United States

ISBN: (纸本)9798350367720

Beyond being merely trendy terms in technology, machine learning (ML) and artificial intelligence (AI) have directly influenced every industry. This article thus demystifies the true meaning of these technologies by sifting through the sultry descriptions. Here, we explore how AI and ML enhance efficiency, decision-making, and problem-solving in various sectors including health, Agriculture, finance, and production as we discover real-world applications. Continuing with the discussion of implementation challenges, the aspects of bias, ethical pitfalls, and report cards are examined. In addition, the article also covered how the integration of AI as well as ML remains a way of improving processes, creating better user experiences, and spurring innovation. This paper, which is also based on case studies, discusses the relationship between social welfare and AI and the importance of AI's development and use being done responsibly. Considering all the discussed aspects, this volume provides a rather nuanced perspective on AI and ML, unmasking the myths around these concepts to reveal the fact that they have a highly significant impact on the current reality and its projected evolutions. © 2024 IEEE.

关键词： Adversarial machine learning

Uncertainty Quantification For Learned ISTA 33

学校读者我要写书评

暂无评论

Uncertainty Quantification For Learned ISTA

33rd IEEE International Workshop on machine learning for Signal Processing, MLSP 2023

作者： Hoppe, Frederik Verdun, Claudio Mayrink Laus, Hannah Krahmer, Felix Rauhut, Holger Rwth Aachen University Chair of Mathematics of Information Processing Aachen Germany Technical University of Munich Department of Mathematics Munich Germany Munich Center for Machine Learning Munich Germany Munich Data Science Institute Technical University of Munich Munich Germany

ISBN: (纸本)9798350324112

Model-based deep learning solutions to inverse problems have attracted increasing attention in recent years as they bridge state-of-the-art numerical performance with interpretability. In addition, the incorporated prior domain knowledge can make the training more efficient as the smaller number of parameters allows the training step to be executed with smaller datasets. Algorithm unrolling schemes stand out among these model-based learning techniques. Despite their rapid advancement and their close connection to traditional high-dimensional statistical methods, they lack certainty estimates and a theory for uncertainty quantification is still elusive. This work provides a step towards closing this gap proposing a rigorous way to obtain confidence intervals for the LISTA estimator. © 2023 IEEE.

关键词： Deep learning

CENTRAL LIMIT THEOREMS FOR SMOOTH OPTIMAL TRANSPORT MAPS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Manole, Tudor Balakrishnan, Sivaraman Niles-Weed, Jonathan Wasserman, Larry Statistics and Data Science Center Massachusetts Institute of Technology United States Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States Center for Data Science New York University United States Courant Institute of Mathematical Sciences New York University United States

One of the central objects in the theory of optimal transport is the Brenier map: the unique monotone transformation which pushes forward an absolutely continuous probability law onto any other given law. A line of recent work has analyzed L2 convergence rates of plugin estimators of Brenier maps, which are defined as the Brenier map between density estimators of the underlying distributions. In this work, we show that such estimators satisfy a pointwise central limit theorem when the underlying laws are supported on the flat torus of dimension d ≥ 3. We also derive a negative result, showing that these estimators do not converge weakly in L2 when the dimension is sufficiently large. Our proofs hinge upon a quantitative linearization of the Monge-Ampère equation, which may be of independent interest. This result allows us to reduce our problem to that of deriving limit laws for the solution of a uniformly elliptic partial differential equation with a stochastic right-hand side, subject to periodic boundary conditions. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems